New code for 5.10:

- Don't WARN_ON weird states that unprivileged users can create.
 - Don't invalidate page cache when direct writes want to fall back to
   buffered.
 - Fix some problems when readahead ios fail.
 - Fix a problem where inline data pages weren't getting flushed during
   an unshare operation.
 - Rework iomap to support arbitrarily many blocks per page in
   preparation to support THP for the page cache.
 - Fix a bug in the blocksize < pagesize buffered io path where we could
   fail to initialize the many-blocks-per-page uptodate bitmap correctly
   when the backing page is actually up to date.  This could cause us to
   forget to write out dirty pages.
 - Split out the generic_write_sync at the end of the directio write path
   so that btrfs can drop the inode lock before sync'ing the file.
 - Call inode_dio_end before trying to sync the file after a O_DSYNC
   direct write (instead of afterwards) to match the behavior of the
   old directio code.
 -----BEGIN PGP SIGNATURE-----
 
 iQIzBAABCgAdFiEEUzaAxoMeQq6m2jMV+H93GTRKtOsFAl9yB04ACgkQ+H93GTRK
 tOuZxw/+IrBV3HV45PtqQX+HC2F4ebax26cIJrmCQD0neiu16I7H3COjIGN/YOGw
 bN04VirC3bG4BtzVHO/eRHQOCwCevIpP3LkhT6yOfOgkO4Z9Xn/O7E+7uYtgT5Qi
 dBqOFe/aoB6+uHEHaioWUTxF1MlsVqEK/yPWjbSIdQGKFVE03Azj4V5QHtBouF2+
 pNEk7lbBnF0ua3biambeyDO3JTR9dsziIPH8QzQ4M/fMuNLfR2v0s6d4Ol/ndVrC
 Lp3RtThLcioAXh8xSPMO6RVUFfK97SLgNCRngApFbIJn85z9yq7eI7llnhO+XcHF
 FBJ+XottlwJFDt+0xNUaHmjkfUH9GoK8VeFOd3zHvp6xgZZpDkjG2JJk9ZC8Qnn5
 xg4grGngWshNdxFBf8S/O73bAJ1SyRcD5ePYGyMfiij3beGJ0aulKGoYOdDfC/4c
 hHcUc8XpjHSobg5gklQijBif0WIQos1Z4OyDK9d2LqrJOO0NUypO/t2YIdgPFzkj
 rXLmWlKsUYSZyefI5Z8q0AVy7TQGxstS9poC3lkXlsszQ1E5BNup0/bhCGTgCW+5
 az9m41KXxPEDLxieOvIAUhHSSP02IAGQ9Lvvat1GnGfEqShAEWS/IvmIxHDbvyNW
 lZ0NLqNKsItKBH0oIPsrP7fHz2ES1hUIMIaLbApUwKpUcAxrCLY=
 =ocIt
 -----END PGP SIGNATURE-----

Merge tag 'iomap-5.10-merge-4' of git://git.kernel.org/pub/scm/fs/xfs/xfs-linux

Pull iomap updates from Darrick Wong:
 "There's not a lot of new stuff going on here -- a little bit of code
  refactoring to make iomap workable with btrfs' fsync locking model,
  cleanups in preparation for adding THP support for filesystems, and
  fixing a data corruption issue for blocksize < pagesize filesystems.

  Summary:

   - Don't WARN_ON weird states that unprivileged users can create.

   - Don't invalidate page cache when direct writes want to fall back to
     buffered.

   - Fix some problems when readahead ios fail.

   - Fix a problem where inline data pages weren't getting flushed
     during an unshare operation.

   - Rework iomap to support arbitrarily many blocks per page in
     preparation to support THP for the page cache.

   - Fix a bug in the blocksize < pagesize buffered io path where we
     could fail to initialize the many-blocks-per-page uptodate bitmap
     correctly when the backing page is actually up to date. This could
     cause us to forget to write out dirty pages.

   - Split out the generic_write_sync at the end of the directio write
     path so that btrfs can drop the inode lock before sync'ing the
     file.

   - Call inode_dio_end before trying to sync the file after a O_DSYNC
     direct write (instead of afterwards) to match the behavior of the
     old directio code"

* tag 'iomap-5.10-merge-4' of git://git.kernel.org/pub/scm/fs/xfs/xfs-linux:
  iomap: Call inode_dio_end() before generic_write_sync()
  iomap: Allow filesystem to call iomap_dio_complete without i_rwsem
  iomap: Set all uptodate bits for an Uptodate page
  iomap: Change calling convention for zeroing
  iomap: Convert iomap_write_end types
  iomap: Convert write_count to write_bytes_pending
  iomap: Convert read_count to read_bytes_pending
  iomap: Support arbitrarily many blocks per page
  iomap: Use bitmap ops to set uptodate bits
  iomap: Use kzalloc to allocate iomap_page
  fs: Introduce i_blocks_per_page
  iomap: Fix misplaced page flushing
  iomap: Use round_down/round_up macros in __iomap_write_begin
  iomap: Mark read blocks uptodate in write_begin
  iomap: Clear page error before beginning a write
  iomap: Fix direct I/O write consistency check
  iomap: fix WARN_ON_ONCE() from unprivileged users

fs/dax.c

@@ -1037,18 +1037,18 @@ static vm_fault_t dax_load_hole(struct xa_state *xas,
 	return ret;
 }
 
-int dax_iomap_zero(loff_t pos, unsigned offset, unsigned size,
-		   struct iomap *iomap)
+s64 dax_iomap_zero(loff_t pos, u64 length, struct iomap *iomap)
 {
 	sector_t sector = iomap_sector(iomap, pos & PAGE_MASK);
 	pgoff_t pgoff;
 	long rc, id;
 	void *kaddr;
 	bool page_aligned = false;
-
+	unsigned offset = offset_in_page(pos);
+	unsigned size = min_t(u64, PAGE_SIZE - offset, length);
 
 	if (IS_ALIGNED(sector << SECTOR_SHIFT, PAGE_SIZE) &&
-	    IS_ALIGNED(size, PAGE_SIZE))
+	    (size == PAGE_SIZE))
 		page_aligned = true;
 
 	rc = bdev_dax_pgoff(iomap->bdev, sector, PAGE_SIZE, &pgoff);
@@ -1058,8 +1058,7 @@ int dax_iomap_zero(loff_t pos, unsigned offset, unsigned size,
 	id = dax_read_lock();
 
 	if (page_aligned)
-		rc = dax_zero_page_range(iomap->dax_dev, pgoff,
-					 size >> PAGE_SHIFT);
+		rc = dax_zero_page_range(iomap->dax_dev, pgoff, 1);
 	else
 		rc = dax_direct_access(iomap->dax_dev, pgoff, 1, &kaddr, NULL);
 	if (rc < 0) {
@@ -1072,7 +1071,7 @@ int dax_iomap_zero(loff_t pos, unsigned offset, unsigned size,
 		dax_flush(iomap->dax_dev, kaddr + offset, size);
 	}
 	dax_read_unlock(id);
-	return 0;
+	return size;
 }
 
 static loff_t

fs/iomap/buffered-io.c

@@ -22,18 +22,25 @@
 #include "../internal.h"
 
 /*
- * Structure allocated for each page when block size < PAGE_SIZE to track
- * sub-page uptodate status and I/O completions.
+ * Structure allocated for each page or THP when block size < page size
+ * to track sub-page uptodate status and I/O completions.
  */
 struct iomap_page {
-	atomic_t		read_count;
-	atomic_t		write_count;
+	atomic_t		read_bytes_pending;
+	atomic_t		write_bytes_pending;
 	spinlock_t		uptodate_lock;
-	DECLARE_BITMAP(uptodate, PAGE_SIZE / 512);
+	unsigned long		uptodate[];
 };
 
 static inline struct iomap_page *to_iomap_page(struct page *page)
 {
+	/*
+	 * per-block data is stored in the head page.  Callers should
+	 * not be dealing with tail pages (and if they are, they can
+	 * call thp_head() first.
+	 */
+	VM_BUG_ON_PGFLAGS(PageTail(page), page);
+
 	if (page_has_private(page))
 		return (struct iomap_page *)page_private(page);
 	return NULL;
@@ -45,20 +52,16 @@ static struct iomap_page *
 iomap_page_create(struct inode *inode, struct page *page)
 {
 	struct iomap_page *iop = to_iomap_page(page);
+	unsigned int nr_blocks = i_blocks_per_page(inode, page);
 
-	if (iop || i_blocksize(inode) == PAGE_SIZE)
+	if (iop || nr_blocks <= 1)
 		return iop;
 
-	iop = kmalloc(sizeof(*iop), GFP_NOFS | __GFP_NOFAIL);
-	atomic_set(&iop->read_count, 0);
-	atomic_set(&iop->write_count, 0);
+	iop = kzalloc(struct_size(iop, uptodate, BITS_TO_LONGS(nr_blocks)),
+			GFP_NOFS | __GFP_NOFAIL);
 	spin_lock_init(&iop->uptodate_lock);
-	bitmap_zero(iop->uptodate, PAGE_SIZE / SECTOR_SIZE);
-
-	/*
-	 * migrate_page_move_mapping() assumes that pages with private data have
-	 * their count elevated by 1.
-	 */
+	if (PageUptodate(page))
+		bitmap_fill(iop->uptodate, nr_blocks);
 	attach_page_private(page, iop);
 	return iop;
 }
@@ -67,11 +70,14 @@ static void
 iomap_page_release(struct page *page)
 {
 	struct iomap_page *iop = detach_page_private(page);
+	unsigned int nr_blocks = i_blocks_per_page(page->mapping->host, page);
 
 	if (!iop)
 		return;
-	WARN_ON_ONCE(atomic_read(&iop->read_count));
-	WARN_ON_ONCE(atomic_read(&iop->write_count));
+	WARN_ON_ONCE(atomic_read(&iop->read_bytes_pending));
+	WARN_ON_ONCE(atomic_read(&iop->write_bytes_pending));
+	WARN_ON_ONCE(bitmap_full(iop->uptodate, nr_blocks) !=
+			PageUptodate(page));
 	kfree(iop);
 }
 
@@ -142,19 +148,11 @@ iomap_iop_set_range_uptodate(struct page *page, unsigned off, unsigned len)
 	struct inode *inode = page->mapping->host;
 	unsigned first = off >> inode->i_blkbits;
 	unsigned last = (off + len - 1) >> inode->i_blkbits;
-	bool uptodate = true;
 	unsigned long flags;
-	unsigned int i;
 
 	spin_lock_irqsave(&iop->uptodate_lock, flags);
-	for (i = 0; i < PAGE_SIZE / i_blocksize(inode); i++) {
-		if (i >= first && i <= last)
-			set_bit(i, iop->uptodate);
-		else if (!test_bit(i, iop->uptodate))
-			uptodate = false;
-	}
-
-	if (uptodate)
+	bitmap_set(iop->uptodate, first, last - first + 1);
+	if (bitmap_full(iop->uptodate, i_blocks_per_page(inode, page)))
 		SetPageUptodate(page);
 	spin_unlock_irqrestore(&iop->uptodate_lock, flags);
 }
@@ -171,13 +169,6 @@ iomap_set_range_uptodate(struct page *page, unsigned off, unsigned len)
 		SetPageUptodate(page);
 }
 
-static void
-iomap_read_finish(struct iomap_page *iop, struct page *page)
-{
-	if (!iop || atomic_dec_and_test(&iop->read_count))
-		unlock_page(page);
-}
-
 static void
 iomap_read_page_end_io(struct bio_vec *bvec, int error)
 {
@@ -191,7 +182,8 @@ iomap_read_page_end_io(struct bio_vec *bvec, int error)
 		iomap_set_range_uptodate(page, bvec->bv_offset, bvec->bv_len);
 	}
 
-	iomap_read_finish(iop, page);
+	if (!iop || atomic_sub_and_test(bvec->bv_len, &iop->read_bytes_pending))
+		unlock_page(page);
 }
 
 static void
@@ -271,30 +263,19 @@ iomap_readpage_actor(struct inode *inode, loff_t pos, loff_t length, void *data,
 	}
 
 	ctx->cur_page_in_bio = true;
+	if (iop)
+		atomic_add(plen, &iop->read_bytes_pending);
 
-	/*
-	 * Try to merge into a previous segment if we can.
-	 */
+	/* Try to merge into a previous segment if we can */
 	sector = iomap_sector(iomap, pos);
-	if (ctx->bio && bio_end_sector(ctx->bio) == sector)
+	if (ctx->bio && bio_end_sector(ctx->bio) == sector) {
+		if (__bio_try_merge_page(ctx->bio, page, plen, poff,
+				&same_page))
+			goto done;
 		is_contig = true;
-
-	if (is_contig &&
-	    __bio_try_merge_page(ctx->bio, page, plen, poff, &same_page)) {
-		if (!same_page && iop)
-			atomic_inc(&iop->read_count);
-		goto done;
 	}
 
-	/*
-	 * If we start a new segment we need to increase the read count, and we
-	 * need to do so before submitting any previous full bio to make sure
-	 * that we don't prematurely unlock the page.
-	 */
-	if (iop)
-		atomic_inc(&iop->read_count);
-
-	if (!ctx->bio || !is_contig || bio_full(ctx->bio, plen)) {
+	if (!is_contig || bio_full(ctx->bio, plen)) {
 		gfp_t gfp = mapping_gfp_constraint(page->mapping, GFP_KERNEL);
 		gfp_t orig_gfp = gfp;
 		int nr_vecs = (length + PAGE_SIZE - 1) >> PAGE_SHIFT;
@@ -571,13 +552,13 @@ __iomap_write_begin(struct inode *inode, loff_t pos, unsigned len, int flags,
 {
 	struct iomap_page *iop = iomap_page_create(inode, page);
 	loff_t block_size = i_blocksize(inode);
-	loff_t block_start = pos & ~(block_size - 1);
-	loff_t block_end = (pos + len + block_size - 1) & ~(block_size - 1);
+	loff_t block_start = round_down(pos, block_size);
+	loff_t block_end = round_up(pos + len, block_size);
 	unsigned from = offset_in_page(pos), to = from + len, poff, plen;
-	int status;
 
 	if (PageUptodate(page))
 		return 0;
+	ClearPageError(page);
 
 	do {
 		iomap_adjust_read_range(inode, iop, &block_start,
@@ -594,14 +575,13 @@ __iomap_write_begin(struct inode *inode, loff_t pos, unsigned len, int flags,
 			if (WARN_ON_ONCE(flags & IOMAP_WRITE_F_UNSHARE))
 				return -EIO;
 			zero_user_segments(page, poff, from, to, poff + plen);
-			iomap_set_range_uptodate(page, poff, plen);
-			continue;
+		} else {
+			int status = iomap_read_page_sync(block_start, page,
+					poff, plen, srcmap);
+			if (status)
+				return status;
 		}
-
-		status = iomap_read_page_sync(block_start, page, poff, plen,
-				srcmap);
-		if (status)
-			return status;
+		iomap_set_range_uptodate(page, poff, plen);
 	} while ((block_start += plen) < block_end);
 
 	return 0;
@@ -685,9 +665,8 @@ iomap_set_page_dirty(struct page *page)
 }
 EXPORT_SYMBOL_GPL(iomap_set_page_dirty);
 
-static int
-__iomap_write_end(struct inode *inode, loff_t pos, unsigned len,
-		unsigned copied, struct page *page)
+static size_t __iomap_write_end(struct inode *inode, loff_t pos, size_t len,
+		size_t copied, struct page *page)
 {
 	flush_dcache_page(page);
 
@@ -709,15 +688,15 @@ __iomap_write_end(struct inode *inode, loff_t pos, unsigned len,
 	return copied;
 }
 
-static int
-iomap_write_end_inline(struct inode *inode, struct page *page,
-		struct iomap *iomap, loff_t pos, unsigned copied)
+static size_t iomap_write_end_inline(struct inode *inode, struct page *page,
+		struct iomap *iomap, loff_t pos, size_t copied)
 {
 	void *addr;
 
 	WARN_ON_ONCE(!PageUptodate(page));
 	BUG_ON(pos + copied > PAGE_SIZE - offset_in_page(iomap->inline_data));
 
+	flush_dcache_page(page);
 	addr = kmap_atomic(page);
 	memcpy(iomap->inline_data + pos, addr + pos, copied);
 	kunmap_atomic(addr);
@@ -726,13 +705,14 @@ iomap_write_end_inline(struct inode *inode, struct page *page,
 	return copied;
 }
 
-static int
-iomap_write_end(struct inode *inode, loff_t pos, unsigned len, unsigned copied,
-		struct page *page, struct iomap *iomap, struct iomap *srcmap)
+/* Returns the number of bytes copied.  May be 0.  Cannot be an errno. */
+static size_t iomap_write_end(struct inode *inode, loff_t pos, size_t len,
+		size_t copied, struct page *page, struct iomap *iomap,
+		struct iomap *srcmap)
 {
 	const struct iomap_page_ops *page_ops = iomap->page_ops;
 	loff_t old_size = inode->i_size;
-	int ret;
+	size_t ret;
 
 	if (srcmap->type == IOMAP_INLINE) {
 		ret = iomap_write_end_inline(inode, page, iomap, pos, copied);
@@ -811,13 +791,8 @@ iomap_write_actor(struct inode *inode, loff_t pos, loff_t length, void *data,
 
 		copied = iov_iter_copy_from_user_atomic(page, i, offset, bytes);
 
-		flush_dcache_page(page);
-
-		status = iomap_write_end(inode, pos, bytes, copied, page, iomap,
+		copied = iomap_write_end(inode, pos, bytes, copied, page, iomap,
 				srcmap);
-		if (unlikely(status < 0))
-			break;
-		copied = status;
 
 		cond_resched();
 
@@ -891,11 +866,8 @@ iomap_unshare_actor(struct inode *inode, loff_t pos, loff_t length, void *data,
 
 		status = iomap_write_end(inode, pos, bytes, bytes, page, iomap,
 				srcmap);
-		if (unlikely(status <= 0)) {
-			if (WARN_ON_ONCE(status == 0))
-				return -EIO;
-			return status;
-		}
+		if (WARN_ON_ONCE(status == 0))
+			return -EIO;
 
 		cond_resched();
 
@@ -928,11 +900,13 @@ iomap_file_unshare(struct inode *inode, loff_t pos, loff_t len,
 }
 EXPORT_SYMBOL_GPL(iomap_file_unshare);
 
-static int iomap_zero(struct inode *inode, loff_t pos, unsigned offset,
-		unsigned bytes, struct iomap *iomap, struct iomap *srcmap)
+static s64 iomap_zero(struct inode *inode, loff_t pos, u64 length,
+		struct iomap *iomap, struct iomap *srcmap)
 {
 	struct page *page;
 	int status;
+	unsigned offset = offset_in_page(pos);
+	unsigned bytes = min_t(u64, PAGE_SIZE - offset, length);
 
 	status = iomap_write_begin(inode, pos, bytes, 0, &page, iomap, srcmap);
 	if (status)
@@ -944,38 +918,33 @@ static int iomap_zero(struct inode *inode, loff_t pos, unsigned offset,
 	return iomap_write_end(inode, pos, bytes, bytes, page, iomap, srcmap);
 }
 
-static loff_t
-iomap_zero_range_actor(struct inode *inode, loff_t pos, loff_t count,
-		void *data, struct iomap *iomap, struct iomap *srcmap)
+static loff_t iomap_zero_range_actor(struct inode *inode, loff_t pos,
+		loff_t length, void *data, struct iomap *iomap,
+		struct iomap *srcmap)
 {
 	bool *did_zero = data;
 	loff_t written = 0;
-	int status;
 
 	/* already zeroed?  we're done. */
 	if (srcmap->type == IOMAP_HOLE || srcmap->type == IOMAP_UNWRITTEN)
-		return count;
+		return length;
 
 	do {
-		unsigned offset, bytes;
-
-		offset = offset_in_page(pos);
-		bytes = min_t(loff_t, PAGE_SIZE - offset, count);
+		s64 bytes;
 
 		if (IS_DAX(inode))
-			status = dax_iomap_zero(pos, offset, bytes, iomap);
+			bytes = dax_iomap_zero(pos, length, iomap);
 		else
-			status = iomap_zero(inode, pos, offset, bytes, iomap,
-					srcmap);
-		if (status < 0)
-			return status;
+			bytes = iomap_zero(inode, pos, length, iomap, srcmap);
+		if (bytes < 0)
+			return bytes;
 
 		pos += bytes;
-		count -= bytes;
+		length -= bytes;
 		written += bytes;
 		if (did_zero)
 			*did_zero = true;
-	} while (count > 0);
+	} while (length > 0);
 
 	return written;
 }
@@ -1070,7 +1039,7 @@ EXPORT_SYMBOL_GPL(iomap_page_mkwrite);
 
 static void
 iomap_finish_page_writeback(struct inode *inode, struct page *page,
-		int error)
+		int error, unsigned int len)
 {
 	struct iomap_page *iop = to_iomap_page(page);
 
@@ -1079,10 +1048,10 @@ iomap_finish_page_writeback(struct inode *inode, struct page *page,
 		mapping_set_error(inode->i_mapping, -EIO);
 	}
 
-	WARN_ON_ONCE(i_blocksize(inode) < PAGE_SIZE && !iop);
-	WARN_ON_ONCE(iop && atomic_read(&iop->write_count) <= 0);
+	WARN_ON_ONCE(i_blocks_per_page(inode, page) > 1 && !iop);
+	WARN_ON_ONCE(iop && atomic_read(&iop->write_bytes_pending) <= 0);
 
-	if (!iop || atomic_dec_and_test(&iop->write_count))
+	if (!iop || atomic_sub_and_test(len, &iop->write_bytes_pending))
 		end_page_writeback(page);
 }
 
@@ -1116,7 +1085,8 @@ iomap_finish_ioend(struct iomap_ioend *ioend, int error)
 
 		/* walk each page on bio, ending page IO on them */
 		bio_for_each_segment_all(bv, bio, iter_all)
-			iomap_finish_page_writeback(inode, bv->bv_page, error);
+			iomap_finish_page_writeback(inode, bv->bv_page, error,
+					bv->bv_len);
 		bio_put(bio);
 	}
 	/* The ioend has been freed by bio_put() */
@@ -1332,8 +1302,8 @@ iomap_add_to_ioend(struct inode *inode, loff_t offset, struct page *page,
 
 	merged = __bio_try_merge_page(wpc->ioend->io_bio, page, len, poff,
 			&same_page);
-	if (iop && !same_page)
-		atomic_inc(&iop->write_count);
+	if (iop)
+		atomic_add(len, &iop->write_bytes_pending);
 
 	if (!merged) {
 		if (bio_full(wpc->ioend->io_bio, len)) {
@@ -1375,8 +1345,8 @@ iomap_writepage_map(struct iomap_writepage_ctx *wpc,
 	int error = 0, count = 0, i;
 	LIST_HEAD(submit_list);
 
-	WARN_ON_ONCE(i_blocksize(inode) < PAGE_SIZE && !iop);
-	WARN_ON_ONCE(iop && atomic_read(&iop->write_count) != 0);
+	WARN_ON_ONCE(i_blocks_per_page(inode, page) > 1 && !iop);
+	WARN_ON_ONCE(iop && atomic_read(&iop->write_bytes_pending) != 0);
 
 	/*
 	 * Walk through the page to find areas to write back. If we run off the

fs/iomap/direct-io.c

@@ -76,7 +76,7 @@ static void iomap_dio_submit_bio(struct iomap_dio *dio, struct iomap *iomap,
 		dio->submit.cookie = submit_bio(bio);
 }
 
-static ssize_t iomap_dio_complete(struct iomap_dio *dio)
+ssize_t iomap_dio_complete(struct iomap_dio *dio)
 {
 	const struct iomap_dio_ops *dops = dio->dops;
 	struct kiocb *iocb = dio->iocb;
@@ -108,7 +108,7 @@ static ssize_t iomap_dio_complete(struct iomap_dio *dio)
 	 * ->end_io() when necessary, otherwise a racing buffer read would cache
 	 * zeros from unwritten extents.
 	 */
-	if (!dio->error &&
+	if (!dio->error && dio->size &&
 	    (dio->flags & IOMAP_DIO_WRITE) && inode->i_mapping->nrpages) {
 		int err;
 		err = invalidate_inode_pages2_range(inode->i_mapping,
@@ -118,6 +118,7 @@ static ssize_t iomap_dio_complete(struct iomap_dio *dio)
 			dio_warn_stale_pagecache(iocb->ki_filp);
 	}
 
+	inode_dio_end(file_inode(iocb->ki_filp));
 	/*
 	 * If this is a DSYNC write, make sure we push it to stable storage now
 	 * that we've written data.
@@ -125,11 +126,11 @@ static ssize_t iomap_dio_complete(struct iomap_dio *dio)
 	if (ret > 0 && (dio->flags & IOMAP_DIO_NEED_SYNC))
 		ret = generic_write_sync(iocb, ret);
 
-	inode_dio_end(file_inode(iocb->ki_filp));
 	kfree(dio);
 
 	return ret;
 }
+EXPORT_SYMBOL_GPL(iomap_dio_complete);
 
 static void iomap_dio_complete_work(struct work_struct *work)
 {
@@ -388,6 +389,16 @@ iomap_dio_actor(struct inode *inode, loff_t pos, loff_t length,
 		return iomap_dio_bio_actor(inode, pos, length, dio, iomap);
 	case IOMAP_INLINE:
 		return iomap_dio_inline_actor(inode, pos, length, dio, iomap);
+	case IOMAP_DELALLOC:
+		/*
+		 * DIO is not serialised against mmap() access at all, and so
+		 * if the page_mkwrite occurs between the writeback and the
+		 * iomap_apply() call in the DIO path, then it will see the
+		 * DELALLOC block that the page-mkwrite allocated.
+		 */
+		pr_warn_ratelimited("Direct I/O collision with buffered writes! File: %pD4 Comm: %.20s\n",
+				    dio->iocb->ki_filp, current->comm);
+		return -EIO;
 	default:
 		WARN_ON_ONCE(1);
 		return -EIO;
@@ -406,8 +417,8 @@ iomap_dio_actor(struct inode *inode, loff_t pos, loff_t length,
  * Returns -ENOTBLK In case of a page invalidation invalidation failure for
  * writes.  The callers needs to fall back to buffered I/O in this case.
  */
-ssize_t
-iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
+struct iomap_dio *
+__iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 		const struct iomap_ops *ops, const struct iomap_dio_ops *dops,
 		bool wait_for_completion)
 {
@@ -421,14 +432,14 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 	struct iomap_dio *dio;
 
 	if (!count)
-		return 0;
+		return NULL;
 
 	if (WARN_ON(is_sync_kiocb(iocb) && !wait_for_completion))
-		return -EIO;
+		return ERR_PTR(-EIO);
 
 	dio = kmalloc(sizeof(*dio), GFP_KERNEL);
 	if (!dio)
-		return -ENOMEM;
+		return ERR_PTR(-ENOMEM);
 
 	dio->iocb = iocb;
 	atomic_set(&dio->ref, 1);
@@ -558,7 +569,7 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 	dio->wait_for_completion = wait_for_completion;
 	if (!atomic_dec_and_test(&dio->ref)) {
 		if (!wait_for_completion)
-			return -EIOCBQUEUED;
+			return ERR_PTR(-EIOCBQUEUED);
 
 		for (;;) {
 			set_current_state(TASK_UNINTERRUPTIBLE);
@@ -574,10 +585,26 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 		__set_current_state(TASK_RUNNING);
 	}
 
-	return iomap_dio_complete(dio);
+	return dio;
 
 out_free_dio:
 	kfree(dio);
-	return ret;
+	if (ret)
+		return ERR_PTR(ret);
+	return NULL;
+}
+EXPORT_SYMBOL_GPL(__iomap_dio_rw);
+
+ssize_t
+iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
+		const struct iomap_ops *ops, const struct iomap_dio_ops *dops,
+		bool wait_for_completion)
+{
+	struct iomap_dio *dio;
+
+	dio = __iomap_dio_rw(iocb, iter, ops, dops, wait_for_completion);
+	if (IS_ERR_OR_NULL(dio))
+		return PTR_ERR_OR_ZERO(dio);
+	return iomap_dio_complete(dio);
 }
 EXPORT_SYMBOL_GPL(iomap_dio_rw);

fs/jfs/jfs_metapage.c

@@ -473,7 +473,7 @@ static int metapage_readpage(struct file *fp, struct page *page)
 	struct inode *inode = page->mapping->host;
 	struct bio *bio = NULL;
 	int block_offset;
-	int blocks_per_page = PAGE_SIZE >> inode->i_blkbits;
+	int blocks_per_page = i_blocks_per_page(inode, page);
 	sector_t page_start;	/* address of page in fs blocks */
 	sector_t pblock;
 	int xlen;

fs/xfs/xfs_aops.c

@@ -544,7 +544,7 @@ xfs_discard_page(
 			page, ip->i_ino, offset);
 
 	error = xfs_bmap_punch_delalloc_range(ip, start_fsb,
-			PAGE_SIZE / i_blocksize(inode));
+			i_blocks_per_page(inode, page));
 	if (error && !XFS_FORCED_SHUTDOWN(mp))
 		xfs_alert(mp, "page discard unable to remove delalloc mapping.");
 out_invalidate:

include/linux/dax.h

@@ -231,8 +231,7 @@ vm_fault_t dax_finish_sync_fault(struct vm_fault *vmf,
 int dax_delete_mapping_entry(struct address_space *mapping, pgoff_t index);
 int dax_invalidate_mapping_entry_sync(struct address_space *mapping,
 				      pgoff_t index);
-int dax_iomap_zero(loff_t pos, unsigned offset, unsigned size,
-			struct iomap *iomap);
+s64 dax_iomap_zero(loff_t pos, u64 length, struct iomap *iomap);
 static inline bool dax_mapping(struct address_space *mapping)
 {
 	return mapping->host && IS_DAX(mapping->host);

include/linux/iomap.h

@@ -13,6 +13,7 @@
 struct address_space;
 struct fiemap_extent_info;
 struct inode;
+struct iomap_dio;
 struct iomap_writepage_ctx;
 struct iov_iter;
 struct kiocb;
@@ -258,6 +259,10 @@ struct iomap_dio_ops {
 ssize_t iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 		const struct iomap_ops *ops, const struct iomap_dio_ops *dops,
 		bool wait_for_completion);
+struct iomap_dio *__iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
+		const struct iomap_ops *ops, const struct iomap_dio_ops *dops,
+		bool wait_for_completion);
+ssize_t iomap_dio_complete(struct iomap_dio *dio);
 int iomap_dio_iopoll(struct kiocb *kiocb, bool spin);
 
 #ifdef CONFIG_SWAP

include/linux/pagemap.h

@@ -927,4 +927,20 @@ static inline int page_mkwrite_check_truncate(struct page *page,
 	return offset;
 }
 
+/**
+ * i_blocks_per_page - How many blocks fit in this page.
+ * @inode: The inode which contains the blocks.
+ * @page: The page (head page if the page is a THP).
+ *
+ * If the block size is larger than the size of this page, return zero.
+ *
+ * Context: The caller should hold a refcount on the page to prevent it
+ * from being split.
+ * Return: The number of filesystem blocks covered by this page.
+ */
+static inline
+unsigned int i_blocks_per_page(struct inode *inode, struct page *page)
+{
+	return thp_size(page) >> inode->i_blkbits;
+}
 #endif /* _LINUX_PAGEMAP_H */